How to Use the Finnhub MCP in AutoGen

Q: How do AutoGen agents share Finnhub data during a debate?

One agent calls getcompanyprofile and posts the company data to the group chat. The other agents read this message and use the ticker to fetch real-time quotes via getstockquote.

Q: How do AutoGen agents handle conflicting market news from Finnhub?

Your sentiment agent pulls articles using getmarketnews. It then debates the positive and negative headlines with a risk agent to calculate a net sentiment score before executing any trades.

Let your AutoGen agents debate financial trends and stock valuations using real-time Finnhub data through this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Finnhub MCP to AutoGen

Create your Vinkius account to connect Finnhub to AutoGen and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Finnhub with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run consensus-driven market analysis via AutoGen

The `get_basic_financials` tool provides the raw balance sheet numbers that your AutoGen analyst agents use to debate company valuations. A bull agent uses the growth metrics to justify a buy rating, while a bear agent uses the same data to highlight debt risks. This multi-agent setup forces your agents to negotiate and reach a consensus based on hard financial data. Instead of relying on a single model's opinion, you get a balanced investment thesis backed by audited metrics.

Verify market sentiment using this MCP Server

The `get_stock_quote` tool fetches live pricing data to resolve disputes between your trading agents. If a price drop is detected, a news agent calls `get_market_news` to identify the underlying catalyst. The agents debate whether the news justifies a portfolio adjustment or if the price drop is a temporary market blip. This collaborative analysis prevents knee-jerk automated trades based on incomplete data.

Analyze stocks and crypto simultaneously in AutoGen

The `list_crypto_symbols` tool pulls digital asset pairs so your crypto specialist agent can compare token trends against traditional equities. Meanwhile, your stock specialist agent uses `search_symbols` to track related public companies. The two agents exchange data to find correlations between crypto movements and tech stock prices. This cross-asset debate happens entirely within your AutoGen conversation loop, producing highly coordinated trading strategies.

Setup guide

Set up Finnhub MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Finnhub tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Finnhub_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Finnhub data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Finnhub_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Finnhub data")
    print(result.messages[-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Finnhub. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Finnhub now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Finnhub MCP in AutoGen

One agent calls `get_company_profile` and posts the company data to the group chat. The other agents read this message and use the ticker to fetch real-time quotes via `get_stock_quote`.

Yes. You register the tools with specific agents, like your financial analyst agent. Other agents in the AutoGen group must ask that specific analyst to run `get_basic_financials` on their behalf.

Your sentiment agent pulls articles using `get_market_news`. It then debates the positive and negative headlines with a risk agent to calculate a net sentiment score before executing any trades.

Yes. You configure the tools using the AutoGen MCP adapter in your Python script. The agents execute the financial tools in the background without requiring any manual user intervention.

Yes. All agent conversations and financial metrics remain local to your AutoGen environment. The Vinkius MCP Server executes your tool requests securely, keeping your ticker queries and API keys completely isolated.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript